© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4136
    Prev
    Next
    INDEX
    Explanations

    references to health-related topics, particularly probiotics and dietary suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.53
    GOTREF
    -0.53
     againſt
    -0.52
    __':
    
    -0.51
    __":
    -0.50
    industan
    -0.50
     Савезне
    -0.49
    __":
    
    -0.49
    DispatchToProps
    -0.49
    DockStyle
    -0.49
    POSITIVE LOGITS
     paparazzi
    0.50
     comunión
    0.49
     autopilot
    0.46
     perjury
    0.46
    Попис
    0.45
     webcam
    0.45
     Placebo
    0.45
     bodas
    0.44
     chatbot
    0.44
     independencia
    0.44
    Activations Density 6.279%

    No Known Activations